{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RMUHOHSNHWOXAUZZCCXV4AEOCU","short_pith_number":"pith:RMUHOHSN","canonical_record":{"source":{"id":"2106.02713","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T20:48:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"911438d77a807b8b4c688454b516c73a0f4532eaf8991e1e6a1341eeb840b780","abstract_canon_sha256":"876f68f65046fb959c1e8769111522c59b41555dfc8c8a28d7a83b84d011e56b"},"schema_version":"1.0"},"canonical_sha256":"8b28771e4d3d9d70533910af5e008e15188b0ed72d01e7fcec91945bd5be7333","source":{"kind":"arxiv","id":"2106.02713","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02713","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02713v5","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02713","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"RMUHOHSNHWOX","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"RMUHOHSNHWOXAUZZ","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"RMUHOHSN","created_at":"2026-07-05T04:05:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RMUHOHSNHWOXAUZZCCXV4AEOCU","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02713","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T20:48:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"911438d77a807b8b4c688454b516c73a0f4532eaf8991e1e6a1341eeb840b780","abstract_canon_sha256":"876f68f65046fb959c1e8769111522c59b41555dfc8c8a28d7a83b84d011e56b"},"schema_version":"1.0"},"canonical_sha256":"8b28771e4d3d9d70533910af5e008e15188b0ed72d01e7fcec91945bd5be7333","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:11.584648Z","signature_b64":"kG+/tsRdK8OExH6xOU/YYhvE7H8MqiIafl1Tim6GSdtwYui4m9v+d0oBIo5m63v8Jfovkc2+IqO1GSDRQuVoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b28771e4d3d9d70533910af5e008e15188b0ed72d01e7fcec91945bd5be7333","last_reissued_at":"2026-07-05T04:05:11.584193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:11.584193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02713","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCK7/Lop20mhu7ltndO23/GbAEiaKwPvTp+pD4fr/BTUQYK+0/KWCDKUrAcBhsBMoNsxxffnMoS2RK7zuttIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:33:56.770378Z"},"content_sha256":"30e46294f8dfd10a59de8737b92b4f5dd8cf162edc08130dae745cb1eb5b83aa","schema_version":"1.0","event_id":"sha256:30e46294f8dfd10a59de8737b92b4f5dd8cf162edc08130dae745cb1eb5b83aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RMUHOHSNHWOXAUZZCCXV4AEOCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Curves for SGD on Structured Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Blake Bordelon, Cengiz Pehlevan","submitted_at":"2021-06-04T20:48:20Z","abstract_excerpt":"The generalization performance of a machine learning algorithm such as a neural network depends in a non-trivial way on the structure of the data distribution. To analyze the influence of data structure on test loss dynamics, we study an exactly solveable model of stochastic gradient descent (SGD) on mean square loss which predicts test loss when training on features with arbitrary covariance structure. We solve the theory exactly for both Gaussian features and arbitrary features and we show that the simpler Gaussian model accurately predicts test loss of nonlinear random-feature models and de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02713","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.02713/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F7wJyQcyQjRXyU7e9CbhRclVBZK5qhMgADcM3eM4lqPZ1LQ84nfZRQT04z68CszpwjlKMAmb6Kz7jkyez7ztDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:33:56.771133Z"},"content_sha256":"104e56e9600c7625e08d72fd5816839cfa43041e604591b10a229a1b439a2e93","schema_version":"1.0","event_id":"sha256:104e56e9600c7625e08d72fd5816839cfa43041e604591b10a229a1b439a2e93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/bundle.json","state_url":"https://pith.science/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T23:33:56Z","links":{"resolver":"https://pith.science/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU","bundle":"https://pith.science/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/bundle.json","state":"https://pith.science/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMUHOHSNHWOXAUZZCCXV4AEOCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RMUHOHSNHWOXAUZZCCXV4AEOCU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"876f68f65046fb959c1e8769111522c59b41555dfc8c8a28d7a83b84d011e56b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T20:48:20Z","title_canon_sha256":"911438d77a807b8b4c688454b516c73a0f4532eaf8991e1e6a1341eeb840b780"},"schema_version":"1.0","source":{"id":"2106.02713","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02713","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02713v5","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02713","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"RMUHOHSNHWOX","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"RMUHOHSNHWOXAUZZ","created_at":"2026-07-05T04:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"RMUHOHSN","created_at":"2026-07-05T04:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:104e56e9600c7625e08d72fd5816839cfa43041e604591b10a229a1b439a2e93","target":"graph","created_at":"2026-07-05T04:05:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.02713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The generalization performance of a machine learning algorithm such as a neural network depends in a non-trivial way on the structure of the data distribution. To analyze the influence of data structure on test loss dynamics, we study an exactly solveable model of stochastic gradient descent (SGD) on mean square loss which predicts test loss when training on features with arbitrary covariance structure. We solve the theory exactly for both Gaussian features and arbitrary features and we show that the simpler Gaussian model accurately predicts test loss of nonlinear random-feature models and de","authors_text":"Blake Bordelon, Cengiz Pehlevan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T20:48:20Z","title":"Learning Curves for SGD on Structured Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02713","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30e46294f8dfd10a59de8737b92b4f5dd8cf162edc08130dae745cb1eb5b83aa","target":"record","created_at":"2026-07-05T04:05:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"876f68f65046fb959c1e8769111522c59b41555dfc8c8a28d7a83b84d011e56b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-04T20:48:20Z","title_canon_sha256":"911438d77a807b8b4c688454b516c73a0f4532eaf8991e1e6a1341eeb840b780"},"schema_version":"1.0","source":{"id":"2106.02713","kind":"arxiv","version":5}},"canonical_sha256":"8b28771e4d3d9d70533910af5e008e15188b0ed72d01e7fcec91945bd5be7333","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b28771e4d3d9d70533910af5e008e15188b0ed72d01e7fcec91945bd5be7333","first_computed_at":"2026-07-05T04:05:11.584193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:11.584193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kG+/tsRdK8OExH6xOU/YYhvE7H8MqiIafl1Tim6GSdtwYui4m9v+d0oBIo5m63v8Jfovkc2+IqO1GSDRQuVoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:11.584648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02713","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30e46294f8dfd10a59de8737b92b4f5dd8cf162edc08130dae745cb1eb5b83aa","sha256:104e56e9600c7625e08d72fd5816839cfa43041e604591b10a229a1b439a2e93"],"state_sha256":"b199f4f36198b8797ac09e420ebe925282ee2152fc3bad40538fbd253886d1b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDfWcZWpr5Lb/pXEpHPlkCUWVTWcnX7bPjDHnin0kvCXxKVWNNZEAI+cmiGdbRlauwAY4yZ/xPzXHjUNbse0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:33:56.809461Z","bundle_sha256":"466e37a55a57a8ae5eba1914b15c75d4c5392814f489187f435218e823be697c"}}